12 KiB
12 KiB
from convlab.base_models.t5.nlu import T5NLU
import requests
def translate_text(text, target_language='en'):
url = 'https://translate.googleapis.com/translate_a/single?client=gtx&sl=auto&tl={}&dt=t&q={}'.format(
target_language, text)
response = requests.get(url)
if response.status_code == 200:
translated_text = response.json()[0][0][0]
return translated_text
else:
return None
class NaturalLanguageAnalyzer:
def predict(self, text, context=None):
# Inicjalizacja modelu NLU
model_name = "ConvLab/t5-small-nlu-multiwoz21"
nlu_model = T5NLU(speaker='user', context_window_size=0, model_name_or_path=model_name)
# Automatyczne tłumaczenie na język angielski
translated_input = translate_text(text)
# Wygenerowanie odpowiedzi z modelu NLU
nlu_output = nlu_model.predict(translated_input)
return nlu_output
def init_session(self):
# Inicjalizacja sesji (jeśli konieczne)
passfrom convlab.util.multiwoz.state import default_state
default_state(){'user_action': [],
'system_action': [],
'belief_state': {'attraction': {'type': '', 'name': '', 'area': ''},
'hotel': {'name': '',
'area': '',
'parking': '',
'price range': '',
'stars': '4',
'internet': 'yes',
'type': 'hotel',
'book stay': '',
'book day': '',
'book people': ''},
'restaurant': {'food': '',
'price range': '',
'name': '',
'area': '',
'book time': '',
'book day': '',
'book people': ''},
'taxi': {'leave at': '',
'destination': '',
'departure': '',
'arrive by': ''},
'train': {'leave at': '',
'destination': '',
'day': '',
'arrive by': '',
'departure': '',
'book people': ''},
'hospital': {'department': ''}},
'booked': {},
'request_state': {},
'terminated': False,
'history': []}import json
import os
from convlab.dst.dst import DST
from convlab.dst.rule.multiwoz.dst_util import normalize_value
class SimpleRuleDST(DST):
def __init__(self):
DST.__init__(self)
self.state = default_state()
self.value_dict = json.load(open('value_dict.json'))
def update(self, user_act=None):
for intent, domain, slot, value in user_act:
domain = domain.lower()
intent = intent.lower()
slot = slot.lower()
if domain not in self.state['belief_state']:
continue
if intent == 'inform':
if slot == 'none' or slot == '':
continue
domain_dic = self.state['belief_state'][domain]
if slot in domain_dic:
nvalue = normalize_value(self.value_dict, domain, slot, value)
self.state['belief_state'][domain][slot] = nvalue
elif intent == 'request':
if domain not in self.state['request_state']:
self.state['request_state'][domain] = {}
if slot not in self.state['request_state'][domain]:
self.state['request_state'][domain][slot] = 0
return self.state
def init_session(self):
self.state = default_state()dst = SimpleRuleDST()
dst.statedst.update([['Inform', 'Hotel', 'Price Range', 'cheap'], ['Inform', 'Hotel', 'Parking', 'yes']])
dst.state['belief_state']['hotel']{'name': '',
'area': '',
'parking': 'yes',
'price range': 'cheap',
'stars': '4',
'internet': 'yes',
'type': 'hotel',
'book stay': '',
'book day': '',
'book people': ''}from collections import defaultdict
import copy
import json
from copy import deepcopy
from convlab.policy.policy import Policy
from convlab.util.multiwoz.dbquery import Database
class SimpleRulePolicy(Policy):
def __init__(self):
Policy.__init__(self)
self.db = Database()
def predict(self, state):
self.results = []
system_action = defaultdict(list)
user_action = defaultdict(list)
for intent, domain, slot, value in state['user_action']:
user_action[(domain.lower(), intent.lower())].append((slot.lower(), value))
for user_act in user_action:
self.update_system_action(user_act, user_action, state, system_action)
# Reguła 3
if any(True for slots in user_action.values() for (slot, _) in slots if slot in ['book stay', 'book day', 'book people']):
if self.results:
system_action = {('Booking', 'Book'): [["Ref", self.results[0].get('Ref', 'N/A')]]}
system_acts = [[intent, domain, slot, value] for (domain, intent), slots in system_action.items() for slot, value in slots]
state['system_action'] = system_acts
return system_acts
def update_system_action(self, user_act, user_action, state, system_action):
domain, intent = user_act
constraints = [(slot, value) for slot, value in state['belief_state'][domain.lower()].items() if value != '']
self.results = deepcopy(self.db.query(domain.lower(), constraints))
# Reguła 1
if intent == 'request':
if len(self.results) == 0:
system_action[(domain, 'NoOffer')] = []
else:
for slot in user_action[user_act]:
if slot[0] in self.results[0]:
system_action[(domain, 'Inform')].append([slot[0], self.results[0].get(slot[0], 'unknown')])
# Reguła 2
elif intent == 'inform':
if len(self.results) == 0:
system_action[(domain, 'NoOffer')] = []
else:
system_action[(domain, 'Inform')].append(['Choice', str(len(self.results))])
choice = self.results[0]
if domain in ["hotel", "attraction", "police", "restaurant"]:
system_action[(domain, 'Recommend')].append(['Name', choice['name']])from convlab.dialog_agent import PipelineAgent
dst.init_session()
policy = SimpleRulePolicy()
agent = PipelineAgent(nlu=None, dst=dst, policy=policy, nlg=None, name='sys')WARNING:root:nlu info_dict is not initialized WARNING:root:dst info_dict is not initialized WARNING:root:policy info_dict is not initialized WARNING:root:nlg info_dict is not initialized
agent.response([['Inform', 'Hotel', 'Price Range', 'cheap'], ['Inform', 'Hotel', 'Parking', 'yes']])[['Inform', 'hotel', 'Choice', '3'], ['Recommend', 'hotel', 'Name', 'huntingdon marriott hotel']]
from convlab.base_models.t5.nlu import T5NLU
from convlab.nlg.template.multiwoz import TemplateNLG
# nlu = T5NLU(speaker='user', context_window_size=0, model_name_or_path='ConvLab/t5-small-nlu-multiwoz21')
nlu = NaturalLanguageAnalyzer()
nlg = TemplateNLG(is_user=False)
agent = PipelineAgent(nlu=nlu, dst=dst, policy=policy, nlg=nlg, name='sys')WARNING:root:nlu info_dict is not initialized WARNING:root:dst info_dict is not initialized WARNING:root:policy info_dict is not initialized WARNING:root:nlg info_dict is not initialized
NLG seed 0
agent.response("I need a cheap hotel with free parking .")'We have 3 such places . Would huntingdon marriott hotel work for you ?'